Pembuatan Model Prediksi Hujan Menggunakan Metode K-Nearest Neighbors

Import Libraries

---

import numpy as np # Numerical Computations
import pandas as pd # Data Preprocessing

# Import libraries for plotting
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px 
import plotly.io as pio
from plotly.subplots import make_subplots
import plotly.graph_objects as go

pio.renderers.default = "plotly_mimetype+notebook_connected"

Import Dataset

---

df = pd.read_csv('weatherAUS.csv')

Eksplorasi Data

---

Preview dataset

df.head()

	Date	Location	MinTemp	MaxTemp	Rainfall	Evaporation	Sunshine	WindGustDir	WindGustSpeed	WindDir9am	...	Humidity9am	Humidity3pm	Pressure9am	Pressure3pm	Cloud9am	Cloud3pm	Temp9am	Temp3pm	RainToday	RainTomorrow
0	2008-12-01	Albury	13.4	22.9	0.6	NaN	NaN	W	44.0	W	...	71.0	22.0	1007.7	1007.1	8.0	NaN	16.9	21.8	No	No
1	2008-12-02	Albury	7.4	25.1	0.0	NaN	NaN	WNW	44.0	NNW	...	44.0	25.0	1010.6	1007.8	NaN	NaN	17.2	24.3	No	No
2	2008-12-03	Albury	12.9	25.7	0.0	NaN	NaN	WSW	46.0	W	...	38.0	30.0	1007.6	1008.7	NaN	2.0	21.0	23.2	No	No
3	2008-12-04	Albury	9.2	28.0	0.0	NaN	NaN	NE	24.0	SE	...	45.0	16.0	1017.6	1012.8	NaN	NaN	18.1	26.5	No	No
4	2008-12-05	Albury	17.5	32.3	1.0	NaN	NaN	W	41.0	ENE	...	82.0	33.0	1010.8	1006.0	7.0	8.0	17.8	29.7	No	No

5 rows × 23 columns

Note

Variabel target adalah RainTomorrow.

View dimension of dataset

df.shape

(145460, 23)

Bisa kita lihat bahwa ada 145460 baris dan 23 kolom yang terdapat di dalam dataset.

View column names

col_names = df.columns
col_names

Index(['Date', 'Location', 'MinTemp', 'MaxTemp', 'Rainfall', 'Evaporation',
       'Sunshine', 'WindGustDir', 'WindGustSpeed', 'WindDir9am', 'WindDir3pm',
       'WindSpeed9am', 'WindSpeed3pm', 'Humidity9am', 'Humidity3pm',
       'Pressure9am', 'Pressure3pm', 'Cloud9am', 'Cloud3pm', 'Temp9am',
       'Temp3pm', 'RainToday', 'RainTomorrow'],
      dtype='object')

Checking For datatypes of the attributes

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 145460 entries, 0 to 145459
Data columns (total 23 columns):
 #   Column         Non-Null Count   Dtype  
---  ------         --------------   -----  
 0   Date           145460 non-null  object 
 1   Location       145460 non-null  object 
 2   MinTemp        143975 non-null  float64
 3   MaxTemp        144199 non-null  float64
 4   Rainfall       142199 non-null  float64
 5   Evaporation    82670 non-null   float64
 6   Sunshine       75625 non-null   float64
 7   WindGustDir    135134 non-null  object 
 8   WindGustSpeed  135197 non-null  float64
 9   WindDir9am     134894 non-null  object 
 10  WindDir3pm     141232 non-null  object 
 11  WindSpeed9am   143693 non-null  float64
 12  WindSpeed3pm   142398 non-null  float64
 13  Humidity9am    142806 non-null  float64
 14  Humidity3pm    140953 non-null  float64
 15  Pressure9am    130395 non-null  float64
 16  Pressure3pm    130432 non-null  float64
 17  Cloud9am       89572 non-null   float64
 18  Cloud3pm       86102 non-null   float64
 19  Temp9am        143693 non-null  float64
 20  Temp3pm        141851 non-null  float64
 21  RainToday      142199 non-null  object 
 22  RainTomorrow   142193 non-null  object 
dtypes: float64(16), object(7)
memory usage: 25.5+ MB

• Dapat kita lihat bahwa dataset tersebut berisi campuran variabel kategorikal dan numerik
• Variabel kategorikal memiliki tipe data objek
• Variabel numerik memiliki tipe data float64

View statistical properties of dataset

df.describe()

	MinTemp	MaxTemp	Rainfall	Evaporation	Sunshine	WindGustSpeed	WindSpeed9am	WindSpeed3pm	Humidity9am	Humidity3pm	Pressure9am	Pressure3pm	Cloud9am	Cloud3pm	Temp9am	Temp3pm
count	143975.000000	144199.000000	142199.000000	82670.000000	75625.000000	135197.000000	143693.000000	142398.000000	142806.000000	140953.000000	130395.00000	130432.000000	89572.000000	86102.000000	143693.000000	141851.00000
mean	12.194034	23.221348	2.360918	5.468232	7.611178	40.035230	14.043426	18.662657	68.880831	51.539116	1017.64994	1015.255889	4.447461	4.509930	16.990631	21.68339
std	6.398495	7.119049	8.478060	4.193704	3.785483	13.607062	8.915375	8.809800	19.029164	20.795902	7.10653	7.037414	2.887159	2.720357	6.488753	6.93665
min	-8.500000	-4.800000	0.000000	0.000000	0.000000	6.000000	0.000000	0.000000	0.000000	0.000000	980.50000	977.100000	0.000000	0.000000	-7.200000	-5.40000
25%	7.600000	17.900000	0.000000	2.600000	4.800000	31.000000	7.000000	13.000000	57.000000	37.000000	1012.90000	1010.400000	1.000000	2.000000	12.300000	16.60000
50%	12.000000	22.600000	0.000000	4.800000	8.400000	39.000000	13.000000	19.000000	70.000000	52.000000	1017.60000	1015.200000	5.000000	5.000000	16.700000	21.10000
75%	16.900000	28.200000	0.800000	7.400000	10.600000	48.000000	19.000000	24.000000	83.000000	66.000000	1022.40000	1020.000000	7.000000	7.000000	21.600000	26.40000
max	33.900000	48.100000	371.000000	145.000000	14.500000	135.000000	130.000000	87.000000	100.000000	100.000000	1041.00000	1039.600000	9.000000	9.000000	40.200000	46.70000

Explore Categorical Variables

categorical = df.select_dtypes(include=['object'])
categorical.head()

	Date	Location	WindGustDir	WindDir9am	WindDir3pm	RainToday	RainTomorrow
0	2008-12-01	Albury	W	W	WNW	No	No
1	2008-12-02	Albury	WNW	NNW	WSW	No	No
2	2008-12-03	Albury	WSW	W	WSW	No	No
3	2008-12-04	Albury	NE	SE	E	No	No
4	2008-12-05	Albury	W	ENE	NW	No	No

• Terdapat 6 variabel kategorikal dalam dataset. Variabel-variabel tersebut adalah: Lokasi, WindGustDir, WindDir9am, WindDir3pm, RainToday, dan RainTomorrow.
• Ada dua variabel kategorikal biner yaitu RainToday dan RainTomorrow
• RainTomorrow adalah variabel target

Missing values in Categorical Variables

categorical.isna().sum().to_frame('number of null values')

	number of null values
Date	0
Location	0
WindGustDir	10326
WindDir9am	10566
WindDir3pm	4228
RainToday	3261
RainTomorrow	3267

Explore Numerical Variables

Numerical = df.select_dtypes(include=['float64','int'])
Numerical.head()

	MinTemp	MaxTemp	Rainfall	Evaporation	Sunshine	WindGustSpeed	WindSpeed9am	WindSpeed3pm	Humidity9am	Humidity3pm	Pressure9am	Pressure3pm	Cloud9am	Cloud3pm	Temp9am	Temp3pm
0	13.4	22.9	0.6	NaN	NaN	44.0	20.0	24.0	71.0	22.0	1007.7	1007.1	8.0	NaN	16.9	21.8
1	7.4	25.1	0.0	NaN	NaN	44.0	4.0	22.0	44.0	25.0	1010.6	1007.8	NaN	NaN	17.2	24.3
2	12.9	25.7	0.0	NaN	NaN	46.0	19.0	26.0	38.0	30.0	1007.6	1008.7	NaN	2.0	21.0	23.2
3	9.2	28.0	0.0	NaN	NaN	24.0	11.0	9.0	45.0	16.0	1017.6	1012.8	NaN	NaN	18.1	26.5
4	17.5	32.3	1.0	NaN	NaN	41.0	7.0	20.0	82.0	33.0	1010.8	1006.0	7.0	8.0	17.8	29.7

Missing values in numerical variables

Numerical.isnull().sum()

MinTemp           1485
MaxTemp           1261
Rainfall          3261
Evaporation      62790
Sunshine         69835
WindGustSpeed    10263
WindSpeed9am      1767
WindSpeed3pm      3062
Humidity9am       2654
Humidity3pm       4507
Pressure9am      15065
Pressure3pm      15028
Cloud9am         55888
Cloud3pm         59358
Temp9am           1767
Temp3pm           3609
dtype: int64

Check for duplicated values

df[df.duplicated()]

	Date	Location	MinTemp	MaxTemp	Rainfall	Evaporation	Sunshine	WindGustDir	WindGustSpeed	WindDir9am	...	Humidity9am	Humidity3pm	Pressure9am	Pressure3pm	Cloud9am	Cloud3pm	Temp9am	Temp3pm	RainToday	RainTomorrow

0 rows × 23 columns

Data tidak mengandung duplikasi antar atribut

Visualisasi Data

---

Date Plot

df_dateplot = df.iloc[-950:,:]
plt.figure(figsize=[20,5])
plt.plot(df_dateplot['Date'],df_dateplot['MinTemp'],color='blue',linewidth=1, label= 'MinTemp')
plt.plot(df_dateplot['Date'],df_dateplot['MaxTemp'],color='red',linewidth=1, label= 'MaxTemp')
plt.fill_between(df_dateplot['Date'],df_dateplot['MinTemp'],df_dateplot['MaxTemp'], facecolor = '#EBF78F')
plt.title('MinTemp vs MaxTemp by Date')
plt.legend(loc='lower left', frameon=False)
plt.show()

• Plot di atas menunjukkan bahwa temperatur minimal dan maksimal relatif meningkat dan menurun setiap tahunnya.
• Kondisi cuaca selalu berlawanan di kedua bagian. Seperti Australia yang terletak di belahan bumi bagian selatan musim-musimnya sedikit berbeda.
• Seperti yang dapat kita lihat bahwa dari Desember hingga Februari adalah musim panas, dari Maret hingga Mei adalah musim gugur, dari Juni hingga Agustus adalah musim dingin, dan dari September hingga November adalah musim semi.

Visualisasi Distribusi Variabel Numerik

def plot_numerical_distributions(df):
    # Get numerical columns
    numerical_cols = df.select_dtypes(include=['float64']).columns
    
    # Calculate number of rows and columns needed for subplots
    n_plots = len(numerical_cols)
    n_cols = 4  # keeping 4 columns as in original
    n_rows = int(np.ceil(n_plots / n_cols))
    
    # Create subplots
    fig = make_subplots(rows=n_rows, cols=n_cols, 
                       subplot_titles=numerical_cols,
                       vertical_spacing=0.1,
                       horizontal_spacing=0.05)
    
    # Current position tracker
    row = 1
    col = 1
    
    for col_name in numerical_cols:
        # Remove NaN values for this column
        clean_data = df[col_name].dropna()
        
        if len(clean_data) > 0:  # Only create plot if we have non-NaN values
            # Create histogram with KDE
            hist = go.Histogram(x=clean_data, 
                              name=col_name,
                              nbinsx=30,
                              histnorm='probability density')
            
            # Calculate KDE only if we have enough data points
            if len(clean_data) > 1:
                kde_points = np.linspace(clean_data.min(), clean_data.max(), 100)
                kde = np.histogram(clean_data, bins=30, density=True)[0]
                
                # Add KDE line
                kde_line = go.Scatter(x=kde_points, 
                                    y=np.interp(kde_points, 
                                              np.linspace(clean_data.min(), 
                                                        clean_data.max(), 
                                                        30),
                                              kde),
                                    name=f'{col_name}_kde',
                                    line=dict(color='red'))
                
                # Add traces to subplot
                fig.add_trace(hist, row=row, col=col)
                fig.add_trace(kde_line, row=row, col=col)
            else:
                # If not enough data points for KDE, just add histogram
                fig.add_trace(hist, row=row, col=col)
        
        # Update position for next plot
        if col == n_cols:
            col = 1
            row += 1
        else:
            col += 1
    
    # Update layout
    fig.update_layout(
        height=500 * n_rows,  # Adjust height based on number of rows
        width=1600,          # Fixed width
        showlegend=False,
        title_text="Distribusi Variabel Numerik"
    )
    
    # Update axes labels
    fig.update_xaxes(title_text="Value")
    fig.update_yaxes(title_text="Density")
    
    return fig

numeric_dist_fig = plot_numerical_distributions(df)
numeric_dist_fig.show()

Visualize frequency distribution of RainTomorrow variable

value_counts = df['RainTomorrow'].value_counts(dropna=False)

distribution = value_counts.reset_index()
distribution.columns = ['RainTomorrow', 'Count']

distribution['RainTomorrow'] = distribution['RainTomorrow'].fillna('Null')

bar_chart = px.bar(
    distribution,
    x='RainTomorrow',
    y='Count',
    title='Distribusi variabel RainTomorrow',
    labels={'RainTomorrow': 'Rain Tomorrow', 'Count': 'Count'},
    text='Count'
)
bar_chart.update_traces(textposition='outside')

pie_chart = px.pie(
    distribution,
    names='RainTomorrow',
    values='Count',
    title='Distribusi variabel RainTomorrow'
)

bar_chart.show()
pie_chart.show()

Pembuatan Model

---

Preprocessing

Memisah data menjadi fitur (X) dan target (y)

X = df.drop(columns=['Date', 'RainTomorrow'])
y = df['RainTomorrow']

display("X")
display(X.head())

display("Y")
display(y.head())

'X'

	Location	MinTemp	MaxTemp	Rainfall	Evaporation	Sunshine	WindGustDir	WindGustSpeed	WindDir9am	WindDir3pm	...	WindSpeed3pm	Humidity9am	Humidity3pm	Pressure9am	Pressure3pm	Cloud9am	Cloud3pm	Temp9am	Temp3pm	RainToday
0	Albury	13.4	22.9	0.6	NaN	NaN	W	44.0	W	WNW	...	24.0	71.0	22.0	1007.7	1007.1	8.0	NaN	16.9	21.8	No
1	Albury	7.4	25.1	0.0	NaN	NaN	WNW	44.0	NNW	WSW	...	22.0	44.0	25.0	1010.6	1007.8	NaN	NaN	17.2	24.3	No
2	Albury	12.9	25.7	0.0	NaN	NaN	WSW	46.0	W	WSW	...	26.0	38.0	30.0	1007.6	1008.7	NaN	2.0	21.0	23.2	No
3	Albury	9.2	28.0	0.0	NaN	NaN	NE	24.0	SE	E	...	9.0	45.0	16.0	1017.6	1012.8	NaN	NaN	18.1	26.5	No
4	Albury	17.5	32.3	1.0	NaN	NaN	W	41.0	ENE	NW	...	20.0	82.0	33.0	1010.8	1006.0	7.0	8.0	17.8	29.7	No

5 rows × 21 columns

'Y'

0    No
1    No
2    No
3    No
4    No
Name: RainTomorrow, dtype: object

Memisahkan data menjadi training data dan testing data

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 37)

X_train

	Location	MinTemp	MaxTemp	Rainfall	Evaporation	Sunshine	WindGustDir	WindGustSpeed	WindDir9am	WindDir3pm	...	WindSpeed3pm	Humidity9am	Humidity3pm	Pressure9am	Pressure3pm	Cloud9am	Cloud3pm	Temp9am	Temp3pm	RainToday
22861	NorfolkIsland	19.8	26.6	0.0	6.0	11.1	SW	26.0	WNW	SSW	...	19.0	74.0	74.0	1012.4	1011.5	1.0	3.0	24.7	26.2	No
92291	GoldCoast	18.4	25.5	0.0	NaN	NaN	NE	33.0	NW	NE	...	26.0	61.0	61.0	1019.2	1015.5	NaN	NaN	21.0	23.7	No
84611	Brisbane	23.6	29.1	0.0	6.6	3.2	SE	43.0	SE	SE	...	13.0	67.0	73.0	1021.3	1020.8	7.0	7.0	25.9	24.4	No
102633	Nuriootpa	10.8	23.4	0.0	9.0	11.0	WSW	41.0	SSE	WSW	...	6.0	64.0	30.0	1016.7	1014.7	2.0	3.0	15.3	23.3	No
16017	Newcastle	4.2	19.9	0.0	NaN	NaN	NaN	NaN	NW	NaN	...	0.0	78.0	42.0	NaN	NaN	0.0	0.0	9.5	19.0	No
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
108888	Albany	12.0	17.1	0.0	3.4	3.3	NaN	NaN	W	N	...	20.0	78.0	79.0	1025.4	1024.5	8.0	5.0	14.5	16.0	No
85546	Brisbane	13.9	28.7	0.0	6.8	12.0	NE	22.0	N	NNE	...	11.0	45.0	46.0	1020.9	1015.8	0.0	0.0	24.1	26.5	No
104899	Nuriootpa	8.5	13.4	4.4	3.4	2.4	NW	43.0	NNW	N	...	11.0	77.0	91.0	1006.1	1001.4	4.0	8.0	10.3	9.8	Yes
120483	PerthAirport	15.8	26.3	0.0	9.2	13.0	SW	52.0	S	SW	...	28.0	56.0	37.0	1010.1	1010.5	1.0	1.0	21.9	24.8	No
20843	NorahHead	15.9	19.1	0.0	NaN	NaN	SSW	65.0	SW	SSW	...	44.0	58.0	72.0	1010.9	1009.9	NaN	NaN	17.6	18.2	No

116368 rows × 21 columns

Memisahkan fitur numerik dan kategorikal

numerical_cols = X.select_dtypes(include=['float64']).columns
categorical_cols = X.select_dtypes(include=['object', 'category']).columns

display(numerical_cols)
display(categorical_cols)

Index(['MinTemp', 'MaxTemp', 'Rainfall', 'Evaporation', 'Sunshine',
       'WindGustSpeed', 'WindSpeed9am', 'WindSpeed3pm', 'Humidity9am',
       'Humidity3pm', 'Pressure9am', 'Pressure3pm', 'Cloud9am', 'Cloud3pm',
       'Temp9am', 'Temp3pm'],
      dtype='object')

Index(['Location', 'WindGustDir', 'WindDir9am', 'WindDir3pm', 'RainToday'], dtype='object')

Melakukan imputasi terhadap fitur numerik

from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OneHotEncoder, LabelEncoder
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score

num_imputer = SimpleImputer(strategy='median')
X_train_num = pd.DataFrame(num_imputer.fit_transform(X_train[numerical_cols]), columns=numerical_cols)
X_test_num = pd.DataFrame(num_imputer.transform(X_test[numerical_cols]), columns=numerical_cols)

X_train_num[numerical_cols].isnull().sum()

MinTemp          0
MaxTemp          0
Rainfall         0
Evaporation      0
Sunshine         0
WindGustSpeed    0
WindSpeed9am     0
WindSpeed3pm     0
Humidity9am      0
Humidity3pm      0
Pressure9am      0
Pressure3pm      0
Cloud9am         0
Cloud3pm         0
Temp9am          0
Temp3pm          0
dtype: int64

Melakukan imputasi terhadap fitur kategorikal

cat_imputer = SimpleImputer(strategy='most_frequent')
X_train_cat_imputed = pd.DataFrame(cat_imputer.fit_transform(X_train[categorical_cols]), columns=categorical_cols)
X_test_cat_imputed = pd.DataFrame(cat_imputer.transform(X_test[categorical_cols]), columns=categorical_cols)

X_train_cat_imputed[categorical_cols].isnull().sum()

Location       0
WindGustDir    0
WindDir9am     0
WindDir3pm     0
RainToday      0
dtype: int64

Encode fitur kategorikal menggunakan OneHotEncoder

onehot_encoder = OneHotEncoder(handle_unknown='ignore', sparse_output=False)
X_train_cat_encoded = pd.DataFrame(onehot_encoder.fit_transform(X_train_cat_imputed),
                                   columns=onehot_encoder.get_feature_names_out(categorical_cols))
X_test_cat_encoded = pd.DataFrame(onehot_encoder.transform(X_test_cat_imputed),
                                  columns=onehot_encoder.get_feature_names_out(categorical_cols))

X_train_cat_encoded

	Location_Adelaide	Location_Albany	Location_Albury	Location_AliceSprings	Location_BadgerysCreek	Location_Ballarat	Location_Bendigo	Location_Brisbane	Location_Cairns	Location_Canberra	...	WindDir3pm_S	WindDir3pm_SE	WindDir3pm_SSE	WindDir3pm_SSW	WindDir3pm_SW	WindDir3pm_W	WindDir3pm_WNW	WindDir3pm_WSW	RainToday_No	RainToday_Yes
0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	1.0	0.0
1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
2	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	...	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
3	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	1.0	0.0
4	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
116363	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
116364	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
116365	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0
116366	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	1.0	0.0
116367	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	1.0	0.0

116368 rows × 99 columns

Menggabungkan fitur yang sudah dipreproses

X_train_processed = pd.concat([X_train_num, X_train_cat_encoded], axis=1)
X_test_processed = pd.concat([X_test_num, X_test_cat_encoded], axis=1)

X_train_processed

	MinTemp	MaxTemp	Rainfall	Evaporation	Sunshine	WindGustSpeed	WindSpeed9am	WindSpeed3pm	Humidity9am	Humidity3pm	...	WindDir3pm_S	WindDir3pm_SE	WindDir3pm_SSE	WindDir3pm_SSW	WindDir3pm_SW	WindDir3pm_W	WindDir3pm_WNW	WindDir3pm_WSW	RainToday_No	RainToday_Yes
0	19.8	26.6	0.0	6.0	11.1	26.0	11.0	19.0	74.0	74.0	...	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	1.0	0.0
1	18.4	25.5	0.0	4.8	8.4	33.0	9.0	26.0	61.0	61.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
2	23.6	29.1	0.0	6.6	3.2	43.0	13.0	13.0	67.0	73.0	...	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
3	10.8	23.4	0.0	9.0	11.0	41.0	15.0	6.0	64.0	30.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	1.0	0.0
4	4.2	19.9	0.0	4.8	8.4	39.0	2.0	0.0	78.0	42.0	...	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
116363	12.0	17.1	0.0	3.4	3.3	39.0	4.0	20.0	78.0	79.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
116364	13.9	28.7	0.0	6.8	12.0	22.0	6.0	11.0	45.0	46.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
116365	8.5	13.4	4.4	3.4	2.4	43.0	15.0	11.0	77.0	91.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0
116366	15.8	26.3	0.0	9.2	13.0	52.0	28.0	28.0	56.0	37.0	...	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	1.0	0.0
116367	15.9	19.1	0.0	4.8	8.4	65.0	24.0	44.0	58.0	72.0	...	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	1.0	0.0

116368 rows × 115 columns

Melakukan imputasi terhadap target variabel

target_imputer = SimpleImputer(strategy='most_frequent')
y_train_imputed = target_imputer.fit_transform(y_train.values.reshape(-1, 1)).flatten()  # Fit to train
y_test_imputed = target_imputer.transform(y_test.values.reshape(-1, 1)).flatten()

np.unique(y_train_imputed)

array(['No', 'Yes'], dtype=object)

Encode target variabel menggunakan LabelEncoder

label_encoder = LabelEncoder()
y_train_encoded = label_encoder.fit_transform(y_train_imputed)
y_test_encoded = label_encoder.transform(y_test_imputed)

y_train_encoded

array([0, 0, 1, ..., 1, 0, 0], shape=(116368,))

Pelatihan dan Evaluasi Model

Latih model dengan menggunakan KNN

knn = KNeighborsClassifier()
knn.fit(X_train_processed, y_train_encoded)
y_pred_enc = knn.predict(X_test_processed)
y_pred_enc

array([0, 0, 0, ..., 0, 0, 0], shape=(29092,))

Hasil

from sklearn.metrics import accuracy_score, confusion_matrix, roc_auc_score, ConfusionMatrixDisplay, precision_score, recall_score, f1_score, classification_report, roc_curve, auc, precision_recall_curve, average_precision_score
from sklearn.metrics import accuracy_score, roc_auc_score, cohen_kappa_score, RocCurveDisplay, classification_report

accuracy = accuracy_score(y_test_encoded, y_pred_enc)
cm = confusion_matrix(y_test_encoded, y_pred_enc)
roc_auc = roc_auc_score(y_test_encoded, y_pred_enc)

display("Accuracy: " + str(accuracy))
disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=knn.classes_)
disp.plot(cmap=plt.cm.Blues)

roc_disp = RocCurveDisplay.from_predictions(y_test_encoded, y_pred_enc)
plt.show()

'Accuracy: 0.8399216279389523'

Mencoba tuning KNN dengan menggunakan parameter

knn = KNeighborsClassifier(n_neighbors=4, metric="manhattan")
knn.fit(X_train_processed, y_train_encoded)
y_pred_enc = knn.predict(X_test_processed)

0.8418121820431734

Hasil

from sklearn.metrics import accuracy_score, confusion_matrix, roc_auc_score, ConfusionMatrixDisplay, precision_score, recall_score, f1_score, classification_report, roc_curve, auc, precision_recall_curve, average_precision_score
from sklearn.metrics import accuracy_score, roc_auc_score, cohen_kappa_score, RocCurveDisplay, classification_report

accuracy = accuracy_score(y_test_encoded, y_pred_enc)
cm = confusion_matrix(y_test_encoded, y_pred_enc)
roc_auc = roc_auc_score(y_test_encoded, y_pred_enc)

display("Accuracy: " + str(accuracy))
disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=knn.classes_)
disp.plot(cmap=plt.cm.Blues)

roc_disp = RocCurveDisplay.from_predictions(y_test_encoded, y_pred_enc)
plt.show()

'Accuracy: 0.8418121820431734'